Hypothesis inference for vehicles

1. A method for determining a state of a vehicle on a road portion having two or more lanes, the vehicle comprising an Automated Driving System (ADS) feature, the method comprising: obtaining map data associated with the road portion; obtaining positioning data indicating a position of the vehicle on the road; obtaining sensor data from a sensor system of the vehicle; initializing a filter per lane of the road portion based on the obtained map data, the obtained positioning data, and the obtained sensor data, wherein each filter indicates an estimated state of the vehicle on the road portion; selecting one of the initialized filters by means of a trained machine-learning algorithm configured to use the obtained map data, the obtained positioning data, the obtained sensor data, and each estimated state as indicated by each filter as input and to output a single selected initialized filter indicative of a current state of the vehicle on the road portion; controlling the ADS feature of the vehicle based on the selected initialized filter.

2. The method according to claim 1, wherein each initialized filter is one of a Bayesian filter and a combination of multiple Bayesian filters.

3. The method according to claim 2, wherein each Bayesian filter is one of Kalman Filter, Extended Kalman Filter (EKF), Unscented Kalman Filter (UKF), Cubature Kalman Filter (CKF), and Particle Filter (PF).

4. The method according to claim 1, wherein the obtained sensor data comprises information about a state of one or more other vehicles in the surrounding environment of the vehicle, lane marker geometry, lane marker type, traffic sign information, road barrier information, and Inertial Measurement Unit (IMU) data.

5. The method according to claim 1, wherein initializing the filter per lane of the road portion comprises, for each filter: continuously obtaining the positioning data of the vehicle on the road over time; obtaining sensor data comprising at least one of acceleration and velocity of the vehicle; and determining an in-lane longitudinal position of the vehicle on the road portion.

6. The method according to claim 5, wherein initializing the filter per lane of the road portion comprises, for each filter: obtaining sensor data comprising the lane marker geometry and a relative distance of the vehicle from the lane markers on the road portion; and determining an in-lane lateral position and an in-lane heading of the vehicle on the road portion.

7. The method according to claim 6, wherein each filter is initialized based on the determined longitudinal position and in-lane lateral position and heading of the vehicle on the road portion for each filter.

8. The method according to claim 1, wherein the map data comprises high definition (HD) map data.

9. The method according to claim 1, further comprising: obtaining a signal indicative of a desired activation of the ADS feature; wherein the step of controlling the ADS feature comprises activating the ADS feature after the selection of the initialized filter has been made and using the selected initialized filter to indicate the vehicle's state on the road.

10. A non-transitory computer-readable storage medium storing one or more programs configured to be executed by one or more processors of an in-vehicle processing system, the one or more programs comprising instructions for performing the method according to claim 1.

11. A system for determining a state of a vehicle on a road portion having two or more lanes, the vehicle comprising an Automated Driving System (ADS) feature, the system comprising control circuitry configured to: obtain map data associated with the road portion; obtain positioning data indicating a position of the vehicle on the road; obtain sensor data from a sensor system of the vehicle; initialize a filter per lane of the road portion based on the obtained map data, the obtained positioning data, and the obtained sensor data, wherein each filter indicates an estimated state of the vehicle on the road portion; select one of the initialized filters by means of a trained machine-learning algorithm configured to use the obtained map data, the obtained positioning data, the obtained sensor data, and each estimated state as indicated by each filter as input and to output a single selected initialized filter indicative of a current state of the vehicle on the road portion; control the ADS feature of the vehicle based on the selected initialized filter.

12. The system according to claim 11, wherein each initialized filter is one of a Bayesian filter and a combination of multiple Bayesian filters.

13. The system according to claim 11, wherein the obtained sensor data comprises information about a state of one or more other vehicles in the surrounding environment of the vehicle, lane marker geometry, lane marker type, traffic sign information, road barrier information, and Inertial Measurement Unit, IMU, data.

14. The system according to claim 11, wherein the control circuitry is further configured to: obtain a signal indicative of a desired activation of the ADS feature; control the ADS feature by activating the ADS feature after the selection of the initialized filter has been made and use the selected initialized filter to indicate the vehicle's state on the road.

15. A vehicle comprising: one or more vehicle-mounted sensors configured to monitor a surrounding environment of the vehicle; a localization system configured to monitor a geographical position and heading of the vehicle; an Automated Driving System (ADS) feature for controlling one or more of acceleration, steering, and braking of the vehicle; and a system according to claim 11.